tweetindex
ES

Sumanth ✓

@Sumanth_077 · AI Engineering → · joined 28 Jul 2021

Simplifying LLMs, Machine Learning & AI Agents for you! • Building https://t.co/9bR9Ad0j4M • Shipping Open Source AI Apps

76 816Followers
874Following
11 401Posts total
327.1KViews on collected posts

Últimas publicaciones

Turn complex documents into agent-ready data! Nutrient turns PDFs and scanned documents into structured data where every extracted field stays linked to the source it came from. The problem with document extraction is that getting the right-looking value is not enough. A https 2.9K views · 26 likes · 19 reposts · 5 replies Open on X →
Turn agent conversations into persistent workspaces! Cohub is an open-source agent OS that gives agents a shared work-site with files, sessions, tools, scheduled tasks, and reusable context. Most agent systems are still centered around conversations. An agent does useful work, 5.8K views · 49 likes · 16 reposts · 6 replies Open on X →
A research agent is only as good as the search layer behind it! I built a Deep Research Agent using LangChain Deep Agents with a search-first architecture designed around grounded, source-backed research. The agent plans the research in real time, breaks the work into smaller h 38.8K views · 435 likes · 79 reposts · 18 replies Open on X →
https://t.co/Qz6DyBHbSO 20.6K views · 27 likes · 6 reposts · 3 replies Open on X →
Clone a human voice in real time without tokenization! VoxCPM is an open-source text-to-speech system that models speech in continuous space instead of discrete tokens. Most TTS systems convert speech to discrete tokens before generation. This quantization creates a fundamental 13.3K views · 186 likes · 27 reposts · 9 replies Open on X →
Your AI agent doesn’t need a better model. It needs a better harness! JIT-Agent is a compact meta-agent that writes your agent harness on the fly. Most agent systems use a fixed scaffold for every task. The same planner, the same memory setup, the same tool orchestration, and h 8.9K views · 99 likes · 28 reposts · 19 replies Open on X →
@Sumanth_077 Great article, Sumanth! 264 views · 1 likes · 0 reposts · 2 replies Open on X →
@Sumanth_077 Great read!! 311 views · 1 likes · 0 reposts · 1 replies Open on X →
@Sumanth_077 Thanks for sharing. 454 views · 3 likes · 0 reposts · 1 replies Open on X →
https://t.co/OJrhmzcTL1 64.1K views · 262 likes · 45 reposts · 11 replies Open on X →
@Sumanth_077 Love this. :))) A lot of AI agent demos look simple until you ask: what does the agent know right now? Context is the product. For us at Dirextalk, that means private rooms where people and AI agents can share the same communication context. 51 views · 1 likes · 0 reposts · 0 replies Open on X →
@Sumanth_077 Building voice agents for real world use is not always straightforward, thanks for sharing this guide. 371 views · 1 likes · 0 reposts · 1 replies Open on X →
@Sumanth_077 Thanks for sharing the project and the demo Sumanth! 371 views · 2 likes · 0 reposts · 1 replies Open on X →
https://t.co/lGawLq9VVA 82.9K views · 162 likes · 25 reposts · 4 replies Open on X →
https://t.co/cHffC3c4N5 2.8K views · 6 likes · 1 reposts · 3 replies Open on X →
Hands on AI Engineering! I open-sourced a collection of 50+ hands-on AI engineering tutorials. It features step-by-step projects and tutorials on: • AI Agents and Multi-agents • RAG (Agentic, Vision, and Local) • MCP AI Agents • OCR Apps • Voice AI Agents • & so much https://t 41.8K views · 767 likes · 151 reposts · 32 replies Open on X →
@Sumanth_077 @grok me explique esse e compare com o pageindex 50 views · 0 likes · 0 reposts · 1 replies Open on X →
If you found it useful, reshare it with your network Follow me → @Sumanth_077 for more such content and tutorials on AI Engineering! https://t.co/8nNR7dbG70 1.3K views · 5 likes · 0 reposts · 0 replies Open on X →
Github Repo: https://t.co/hpr61LdS14 1.3K views · 12 likes · 1 reposts · 1 replies Open on X →
Turn your laptop into a powerful RAG system! LEANN can index and search through millions of documents while using 97% less storage than traditional solutions without accuracy loss. LEANN achieves this through graph-based selective recomputation with high-degree preserving https 13.2K views · 221 likes · 46 reposts · 7 replies Open on X →
@Sumanth_077 Flat chunks lose too much once questions get conceptual. Really like this approach from LightRAG. Great share! 299 views · 2 likes · 0 reposts · 1 replies Open on X →
If you found it useful, reshare it with your network. Follow me → @Sumanth_077 for more such content and tutorials on ML, LLMs and AI Agents! 1.4K views · 6 likes · 0 reposts · 0 replies Open on X →
Github Repo: https://t.co/7X2zEoyagp 1.7K views · 12 likes · 0 reposts · 2 replies Open on X →
Graph-based RAG with dual-level retrieval! LightRAG is an open-source RAG framework that builds knowledge graphs from documents and uses dual-level retrieval to answer both specific and conceptual queries. Traditional RAG relies on vector similarity and flat chunks. This works 24.1K views · 334 likes · 59 reposts · 14 replies Open on X →

Frente a cuentas del mismo tamaño

10 publicaciones de los últimos 90 días, junto al rango de 10K–100K seguidores. llega a más gente que cuentas de su tamaño.

Visualizaciones medianas7 371esta cuenta924mediana de 10K–100K
Alcance, %9.60%esta cuenta3.62%mediana de 10K–100K
Interacción, %1.18%esta cuenta1.52%mediana de 10K–100K
MétricaEsta cuentaMediana de 10K–100KProporción
Visualizaciones medianas por publicación7 3719247.98×
Alcance (visualizaciones ÷ seguidores)9.60%3.62%2.65×
Tasa de interacción1.18%1.52%0.77×

Otras cuentas de este rango →   Comparar con otra cuenta →   Cómo se construyen estas referencias →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

82.9K13 Jul
371
371
5114 Jul
64.1K25 Aug
454
311
26427 Aug
8.9K28 Aug
13.3K30 Aug
20.6K1 Sep
38.8K
5.8K
2.9K3 Sep

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.23%13 Jul
0.81%
0.54%
1.96%14 Jul
0.50%25 Aug
0.88%
0.64%
1.14%27 Aug
1.66%28 Aug
1.69%30 Aug
0.22%1 Sep
1.37%
1.22%
1.72%3 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes39.2%2 620 in total
Reposts7.5%503 in total
Replies2.1%142 in total
Quotes0.5%32 in total
Bookmarks50.7%3 388 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Cuentas similares